Machine-learning-based efficient parameter space exploration for energy storage systems

The increase in energy demand requires developing new storage systems and estimating their remaining energy over their lifetime. The remaining energy of these systems depends on many operating parameters, resulting in a large high-dimensional parameter space to explore. Testing cells exhaustively on a dense grid in the parameter space is prohibitively expensive. This is especially true with considerable cell-to-cell variability in performance, even under the same cycling conditions. Here, we develop a framework based on Gaussian processes, equipped with domain knowledge, and implement Bayesian optimization to explore the parameter space efficiently and quantify remaining energy using failure distributions. Bayesian optimization identifies future experiments that maximize information gain and minimize uncertainty. Experimental results show accurate remaining energy predictions with significantly fewer experiments. However, laboratory cycling conditions, including those in the literature, may not represent real-world cycling. We propose an approach based on laboratory results for predicting remaining energy under real-world cycling conditions. • Efficiently exploring large parameter spaces of energy storage systems • Implementing domain-knowledge-informed Gaussian process and Bayesian optimization • Comparing the prediction performance of different Gaussian process models • Using laboratory cycling to predict cell degradation under real-world cycling Gauging the remaining energy of complex energy storage systems is a key challenge in system development. Alghalayini et al. present a domain-aware Gaussian process coupled with Bayesian optimization to efficiently estimate remaining energy using failure distributions. This approach strategically selects future experiments maximizing information gain for enhanced prediction accuracy.